用大模型生成与真实统计数据一致的微观数据，解决社会科学研究中数据难收集问题。
LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models
- 将大模型视为非参数耦合器，生成符合宏观统计的微观记录
- 通过迭代优化使合成数据在移动、电商、人口等领域的统计匹配度超90%
- 适合经济学、社会学和城市研究者，尤其缺数据时快速构建仿真样本
宏观对齐的微观记录对社会科学和城市研究中的可信模拟至关重要。例如，流行病模型的可靠性取决于个体行为（如出行与接触）与真实情况一致，且总体指标（如病例数或交通流量）与实际数据吻合。然而大规模采集此类细粒度数据不现实，研究者常仅能获得宏观数据。LLMSynthor将预训练大模型转化为具备宏观意识的模拟器，生成与目标宏观统计一致的合成微观记录。该方法迭代构建数据集：每轮由大模型生成一批记录，以最小化合成数据与目标宏观值的偏差。将大模型视为非参数耦合器，可捕捉变量间的复杂联合依赖关系。为提升效率，引入LLM提案采样策略，指导模型有针对性地生成指定变量范围和数量的记录批次，高效修正偏差的同时保留基于模型先验的真实感。在移动、电商、人口等多个领域评估显示，该方法在真实性、统计保真度和实用性方面表现优异，适用于经济学、社会科学与城市研究。
原文摘要 · Abstract (English)
Macro-aligned micro-records are crucial for credible simulations in social science and urban studies. For example, epidemic models are only reliable when individual-level mobility and contacts mirror real behavior, while aggregates match real-world statistics like case counts or travel flows. However, collecting such fine-grained data at scale is impractical, leaving researchers with only macro-level data. LLMSynthor addresses this by turning a pretrained LLM into a macro-aware simulator that generates realistic micro-records consistent with target macro-statistics. It iteratively builds synthetic datasets: in each step, the LLM generates batches of records to minimize discrepancies between synthetic and target aggregates. Treating the LLM as a nonparametric copula allows the model to capture realistic joint dependencies among variables. To improve efficiency, LLM Proposal Sampling guides the LLM to propose targeted record batches, specifying variable ranges and counts, to efficiently correct discrepancies while preserving realism grounded in the model's priors. Evaluations across domains (mobility, e-commerce, population) show that LLMSynthor achieves strong realism, statistical fidelity, and practical utility, making it broadly applicable to economics, social science, and urban studies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。